|
|
|
|
|
from transformers import AutoTokenizer, AutoModelForCausalLM |
|
import torch |
|
device = torch.device("cuda") |
|
model_info = "BAAI/AquilaSQL-7B" |
|
|
|
tokenizer = AutoTokenizer.from_pretrained(model_info, trust_remote_code=True) |
|
model = AutoModelForCausalLM.from_pretrained( |
|
model_info, trust_remote_code=True, torch_dtype=torch.float16, device_map='auto') |
|
|
|
model.eval() |
|
model.to(device) |
|
torch.manual_seed(123) |
|
|
|
text = "有多个数据库表，信息如下：\n表名为cars_data，包含的属性为cars_data.horsepower,cars_data.accelerate,cars_data.mpg,cars_data.id,cars_data.year;表名为continents，包含的属性为continents.contid,continents.continent;表名为countries，包含的属性为countries.continent,countries.countryname,countries.countryid;表名为model_list，包含的属性为model_list.model,model_list.maker,model_list.modelid，它们之间的关系为 countries.continent = continents.contid\n请为下面的问题编写sql查询语句：\n加速度比马力最大的汽车更大的汽车有多少辆？ " |
|
|
|
def generate_prompt(input: str): |
|
prompt = f"A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.###Human: {input}###Assistant:" |
|
return prompt |
|
|
|
stop_tokens = ["###", "[UNK]", "</s>","<|endoftext|>"] |
|
|
|
with torch.no_grad(): |
|
|
|
_input = generate_prompt(text) |
|
tokens = tokenizer.encode_plus(_input, None, max_length=None)['input_ids'] |
|
tokens = torch.tensor(tokens)[None,].to(device) |
|
out = model.generate(tokens, do_sample=False, max_length=1024, eos_token_id=100007,max_new_tokens=512, |
|
bad_words_ids=[[tokenizer.encode(token)[0] for token in stop_tokens]])[0] |
|
out = tokenizer.decode(out.cpu().numpy().tolist()) |
|
print(out) |
|
|
